# Homeassistant Operator

> Safely operate Home Assistant by resolving targets first and validating state before writes.

- Skill: `clawdotnet/homeassistant-operator` (Agent Skill)
- Install (CLI): `npx skillmds@latest add clawdotnet/homeassistant-operator`
- Raw SKILL.md: https://api.skillmd.com/api/skills/clawdotnet/homeassistant-operator/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: clawdotnet (https://skillmd.com/u/clawdotnet)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/clawdotnet/homeassistant-operator

---


When controlling Home Assistant:

1) Prefer read operations before writes:
   - Use `home_assistant.resolve_targets` (area/domain/name) to find valid `entity_id`s.
   - Use `home_assistant.get_state` / `describe_entity` to confirm the current state/attributes.
2) For writes:
   - Use `home_assistant_write.call_services` when acting on multiple targets.
   - Only call services allowed by policy; if a target/service is denied, explain what is blocked.
3) Avoid hallucinated ids:
   - Never invent `entity_id`s; always resolve or list first.
4) Report outcomes:
   - List entities changed + resulting state (or any errors).